Facial emotion recognition (FER) is the task of recognising human emotions from images and videos. Communicating through facial emotions is a kind of non-verbal communication and it reflects a person's inner thoughts and mental states. In the present study, various existing geometric and appearance based feature extraction techniques used in FER are reviewed in tabular form. The main motive of this paper is to analyse the performance of these techniques on the bases of accuracy on different datasets like JAFFE, CK+, CK and MMI. After extensive research on feature extraction techniques for FERS, it is found that the appearance feature-based techniques achieved maximum accuracy and more favourable as compared to geometric feature-based techniques. Finally, the paper concludes with the various challenges encountered for feature extraction in the field of FERS which need to be addressed in the future.
Facial emotion recognition extracts the human emotions from the images and videos. As such, it requires an algorithm to understand and model the relationships between faces and facial expressions, and to recognize human emotions. Recently, deep learning models are extensively utilized enhance the facial emotion recognition rate. However, the deep learning models suffer from the overfitting issue. Moreover, deep learning models perform poorly for images which have poor visibility and noise. Therefore, in this paper, a novel deep learning based facial emotion recognition tool is proposed. Initially, a joint trilateral filter is applied to the obtained dataset to remove the noise. Thereafter, contrast-limited adaptive histogram equalization (CLAHE) is applied to the filtered images to improve the visibility of images. Finally, a deep convolutional neural network is trained. Nadam optimizer is also utilized to optimize the cost function of deep convolutional neural networks. Experiments are achieved by using the benchmark dataset and competitive human emotion recognition models. Comparative analysis demonstrates that the proposed facial emotion recognition model performs considerably better compared to the competitive models.
With the approach of cloud computing, data proprietors are induced to outsource their important information administration systems from adjacent spots to the business open cloud for proficient flexibility. As needs be, enabling a mixed cloud data look organization is of crucial essentialness. Considering the colossal number of data customers and documents in the cloud, it is vital to allow diverse watchwords in the chase request and return reports in the demand of their relevance to these catchphrases. Related wears down accessible encryption focus on single watchword chase or Boolean catchphrase look for, and sometimes sort the rundown things. In this paper, we describe and deal with the testing issue of insurance defending multi-catchphrase situated look for over encoded data in disseminated computing (MRSE).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.